Warning: This document is for an old version of Rasa Core.

HTTP API

Warning

To protect your conversational data, make sure to secure the server. Either by restricting access to the server (e.g. using firewalls) or by enabling one of the authentication methods: Security Considerations.

Note

Before you can use the server, you need to define a domain, create training data, and train a model. You can then use the trained model! See Quickstart for an introduction.

If you are looking for documentation on how to run custom actions - head over to Actions.

The HTTP api exists to make it easy for python and non-python projects to interact with Rasa Core. The API allows you to modify the trackers.

Running the HTTP server

You can run a simple http server that handles requests using your models with:

$ python -m rasa_core.run \
    --enable_api
    -d models/dialogue \
    -u models/nlu/current \
    -o out.log

The different parameters are:

  • --enable_api, enables this additional API
  • -d, which is the path to the Rasa Core model.
  • -u, which is the path to the Rasa NLU model.
  • -o, which is the path to the log file.

Note

If you are using custom actions - make sure to pass in the endpoint configuration for your action server as well using --endpoints endpoints.yml.

Events

Events allow you to modify the internal state of the dialogue. This information will be used to predict the next action. E.g. you can set slots (to store information about the user) or restart the conversation.

You can return multiple events as part of your query, e.g.:

$ curl -XPOST http://localhost:5005/conversations/default/tracker/events -d \
    '{"event": "slot", "name": "cuisine", "value": "mexican"}'

You can find a list of all events and their json representation at Events. You need to send these json formats to the endpoint to log the event.

Security Considerations

We recommend to not expose the Rasa Core server to the outside world but rather connect to it from your backend over a private connection (e.g. between docker containers).

Nevertheless, there are two authentication methods built in:

Token Based Auth:

Pass in the token using --auth_token thisismysecret when starting the server:

$ python -m rasa_core.run \
    --enable_api \
    --auth_token thisismysecret \
    -d models/dialogue \
    -u models/nlu/current \
    -o out.log

Your requests should pass the token, in our case thisismysecret, as a parameter:

$ curl -XGET localhost:5005/conversations/default/tracker?token=thisismysecret

JWT Based Auth:

Enable JWT based authentication using --jwt_secret thisismysecret. Requests to the server need to contain a valid JWT token in the Authorization header that is signed using this secret and the HS256 algorithm.

The user must have username and role attributes. If the role is admin, all endpoints are accessible. If the role is user, endpoints with a sender_id parameter are only accessible if the sender_id matches the user’s username.

$ python -m rasa_core.run \
    --enable_api \
    --jwt_secret thisismysecret \
    -d models/dialogue \
    -u models/nlu/current \
    -o out.log

Your requests should have set a proper JWT header:

"Authorization": "Bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ"
                 "zdWIiOiIxMjM0NTY3ODkwIiwibmFtZSI6IkpvaG4gRG9lIi"
                 "wiaWF0IjoxNTE2MjM5MDIyfQ.qdrr2_a7Sd80gmCWjnDomO"
                 "Gl8eZFVfKXA6jhncgRn-I"

Endpoint Configuration

To connect Rasa Core to other endpoints, you can specify an endpoint configuration within a YAML file. Then run Rasa Core with the flag --endpoints <path to endpoint configuration.yml.

For example:

python -m rasa_core.run \
    --d <core model> \
    --endpoints <path to endpoint configuration>.yml

Note

You can use environment variables within configuration files by specifying them with ${name of environment variable}. These placeholders are then replaced by the value of the environment variable.

Fetching Models From a Server

You can also configure the http server to fetch models from another URL:

$ python -m rasa_core.run \
    --enable_api \
    -d models/dialogue \
    -u models/nlu/current \
    --endpoints my_endpoints.yaml \
    -o out.log

The model server is specified in the endpoint configuration (my_endpoints.yaml), where you specify the server URL Rasa Core regularly queries for zipped Rasa Core models:

models:
  url: http://my-server.com/models/default_core@latest
  wait_time_between_pulls:  10   # [optional](default: 100)

Note

If you want to pull the model just once from the server, set wait_time_between_pulls to None.

Note

Your model server must provide zipped Rasa Core models, and have {"ETag": <model_hash_string>} as one of its headers. Core will only download a new model if this model hash changed.

Rasa Core sends requests to your model server with an If-None-Match header that contains the current model hash. If your model server can provide a model with a different hash from the one you sent, it should send it in as a zip file with an ETag header containing the new hash. If not, Rasa Core expects an empty response with a 204 or 304 status code.

An example request Rasa Core might make to your model server looks like this:

$ curl --header "If-None-Match: d41d8cd98f00b204e9800998ecf8427e" http://my-server.com/models/default_core@latest

Connecting Rasa NLU

To connect Rasa Core with a NLU server, you have to add the connection details into your endpoint configuration file:

nlu:
    url: "http://<your nlu host>:5000"
    token: <token>  # [optional]
    token_name: <name of the token> # [optional] (default: token)

Then run Rasa Core with the --endpoints <path_to_your_endpoint_config>.yml and specify the nlu model to use with the -u flag. For example:

python -m rasa_core.run -d models/current/dialogue \
    -u <project_name>/<model_name> \
    --endpoints endpoints.yml

Connecting a Tracker Store

To configure a tracker store within your endpoint configuration, please see Tracker Stores.

Connecting an Event Broker

To configure an event broker within your endpoint configuration, please see Event Brokers.

Endpoints

Documentation of the server API as OpenAPI Spec.

Have questions or feedback?

We have a very active support community on Rasa Community Forum that is happy to help you with your questions. If you have any feedback for us or a specific suggestion for improving the docs, feel free to share it by creating an issue on Rasa Core GitHub repository.